Malfunction detection apparatus capable of detecting actual malfunctioning device not due to abnormal input values

Abstract

A first classification circuit obtains first measured values from each of devices, the first measured values of the device including at least one input value to the device and at least one output value from the device, and classifies the first measured values of the devices into normal first measured values and outlier first measured values using the OCSVM (One Class nu-Support Vector Machine). A second classification circuit obtains second measured values from each of devices, the second measured values of the device including at least one input value to the device, and classifies the second measured values of the devices into normal second measured values and outlier second measured values using the OCSVM. A determination circuit determines a device having the outlier first measured values and the normal second measured values, to be a malfunctioning device.

1 . A malfunction detection apparatus for detecting a malfunctioning device among a plurality of devices, the malfunction detection apparatus comprising:
 a first classification circuit that obtains first measured values from each one device of the plurality of devices, the first measured values of the one device including at least one input value to the one device and at least one output value from the one device, and classifies the first measured values of the plurality of devices into normal first measured values and outlier first measured values using a predetermined multivariable analysis method;   a second classification circuit that obtains second measured values from each one device of the plurality of devices, the second measured values of the one device including at least one input value to the one device, and classifies the second measured values of the plurality of devices into normal second measured values and outlier second measured values using the multivariable analysis method; and   a determination circuit that determines a device having the outlier first measured values and the normal second measured values, to be a malfunctioning device, among the plurality of devices.   
     
     
         2 . The malfunction detection apparatus as claimed in  claim 1 , wherein the multivariable analysis method is a multivariable analysis method using a one class nu-support vector machine. 
     
     
         3 . The malfunction detection apparatus as claimed in  claim 1 , further comprising a receiver circuit that receives the output values from the plurality of devices, from a plurality of first sensors measuring the output values from the plurality of devices, and receives the input values to the plurality of devices, from a plurality of second sensors measuring the input values to the plurality of devices. 
     
     
         4 . The malfunction detection apparatus as claimed in  claim 3 ,
 wherein the first classification circuit obtains the first measured values from each one device of the plurality of devices, and classifies the first measured values of the plurality of devices into normal first measured values and outlier first measured values, repeatedly every time interval of a predetermined time length;   wherein the second classification circuit obtains the second measured values from each one device of the plurality of devices, and classifies the second measured values of the plurality of devices into normal second measured values and outlier second measured values, repeatedly every time interval of the predetermined time length, and   wherein the determination circuit determines a device having the outlier first measured values and the normal second measured values over a plurality of successive time intervals, to be a malfunctioning device.   
     
     
         5 . The malfunction detection apparatus as claimed in  claim 1 , further comprising an interface that receives a storage medium which is removable,
 wherein the input values to the plurality of devices and the output values from the plurality of devices are read from the storage medium.   
     
     
         6 . An malfunction detection system comprising:
 a plurality of devices,   a plurality of first sensors that measure output values from the plurality of devices, respectively;   a plurality of second sensors that measure input values to the plurality of devices, respectively; and   a malfunction detection apparatus for detecting a malfunctioning device among the plurality of devices,   wherein the malfunction detection apparatus comprises:   a first classification circuit that obtains first measured values from each one device of the plurality of devices, the first measured values of the one device including at least one input value to the one device and at least one output value from the one device, and classifies the first measured values of the plurality of devices into normal first measured values and outlier first measured values using a predetermined multivariable analysis method;   a second classification circuit that obtains second measured values from each one device of the plurality of devices, the second measured values of the one device including at least one input value to the one device, and classifies the second measured values of the plurality of devices into normal second measured values and outlier second measured values using the multivariable analysis method; and   a determination circuit that determines a device having the outlier first measured values and the normal second measured values, to be a malfunctioning device, among the plurality of devices.   
     
     
         7 . The malfunction detection system as claimed in  claim 6 ,
 wherein each one device of the plurality of devices is a secondary battery cell,   wherein each one first sensor of the plurality of first sensors measures at least one of a terminal voltage and a temperature of a secondary battery cell, and   wherein each one second sensor of the plurality of second sensors measures at least one of a charging current, a charged percentage, and an air temperature of a secondary battery cell.   
     
     
         8 . The malfunction detection system as claimed in  claim 6 ,
 wherein each one device of the plurality of devices is a motor device,   wherein each one first sensor of the plurality of first sensors measures at least one of a rotational speed, operation sound, vibration, and a temperature of a motor device, and   wherein each one second sensor of the plurality of second sensors measures at least one of an input current, an input voltage, and an air temperature of a motor device.